What is the accuracy of the Stanford parser? Are its requirements general natural language, software specific or domain specific?
Madhuri Tayal
In some cases it gives wrong answer. because the tagger not parses properly. example the words watch, cut.. etc.
0 votes
0 thanks
Ted Pedersen
It's very accurate. :) However, that depends on the text that you want to parse being at least somewhat similar to the text used to build the models it relies upon. It relies on the usual suspects (newspaper text and some scientific text) so as long as your text is more or less like that the results should be pretty reasonable. Here's more about how it is trained...
http://nlp.stanford.edu/downloads/parser-faq.shtml#z
It's written in Java but you don't need to program anything to run it.
1 votes
1 thanks
- Badges
- Science topic
- Similar topics
- Phytochemistry
- Extracts
More Unnati Shah's questions See All
Similar questions and discussions